Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6055 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.5621. Min Act: -0.1700
Data Index: 1901554 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.5621. Min Act: -0.1700
Data Index: 7009674 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.5308. Min Act: -0.1700
Data Index: 3002164 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.4683. Min Act: -0.1700
Data Index: 6500726 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.4683. Min Act: -0.1700
Data Index: 2946327 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.4058. Min Act: -0.1700
Data Index: 3439934 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3746. Min Act: -0.1700
Data Index: 7009685 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3746. Min Act: -0.1700
Data Index: 3392952 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3433. Min Act: -0.1700
Data Index: 1553242 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3433. Min Act: -0.1700
Data Index: 4172687 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3433. Min Act: -0.1700
Data Index: 708690 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3121. Min Act: -0.1700
Data Index: 282699 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3121. Min Act: -0.1700
Data Index: 5450036 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3433. Min Act: -0.1700
Data Index: 8415057 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3121. Min Act: -0.1700
Data Index: 2048007 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.3121. Min Act: -0.1700
Data Index: 262485 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.2496. Min Act: -0.1700
Data Index: 7954602 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.2496. Min Act: -0.1700
Data Index: 4002629 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.2183. Min Act: -0.1700
Data Index: 2053155 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5621. Min Range: -7.5621
Max Act: 7.2808. Min Act: -0.1700
Data Index: 8430144 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19